Kinect V2-Based Gait Analysis for Children with Cerebral Palsy: Validity and Reliability of Spatial Margin of Stability and Spatiotemporal Variables

Automated Gait Analysis Based on a Marker-Free Pose Estimation Model

Gait analysis is an essential tool for detecting biomechanical irregularities, designing personalized rehabilitation plans, and enhancing athletic performance. Currently, gait assessment depends on either visual observation, which lacks consistency between raters and requires clinical expertise, or instrumented evaluation, which is costly, invasive, time-consuming, and requires specialized equipment and trained personnel. Markerless gait analysis using 2D pose estimation techniques has emerged as a potential solution, but it still requires significant computational resources and human involvement, making it challenging to use. This research proposes an automated method for temporal gait analysis that employs the MediaPipe Pose, a low-computational-resource pose estimation model. The study validated this approach against the Vicon motion capture system to evaluate its reliability. The findings reveal that this approach demonstrates good (ICC_(2,1) > 0.75) to excellent (ICC_(2,1) > 0.90) agreement in all temporal gait parameters except for double support time (right leg switched to left leg) and swing time (right), which only exhibit a moderate (ICC_(2,1) > 0.50) agreement. Additionally, this approach produces temporal gait parameters with low mean absolute error. It will be useful in monitoring changes in gait and evaluating the effectiveness of interventions such as rehabilitation or training programs in the community.

Image-based Gait Spatiotemporal Parameters Estimation using a Single Camera and CNN-Transformer Hybrid Network

Vision-based gait analysis can play an important role in the remote and continuous monitoring of the elderly's health conditions. However, most vision-based approaches compute gait spatiotemporal parameters using human pose information and provide average parameters. This study aimed to propose a straightforward method for stride-by-stride gait spatiotemporal parameters estimation. A total of 160 elderly individuals participated in this study. Data were gathered with a GAITRite system and a mobile camera simultaneously. Three deep learning networks were trained with a few RGB frames as input and a continuous 1D signal containing both spatial and temporal gait parameters as output. The trained networks estimated the stride lengths with correlations of 0.938 and more and detected gait events with F1-scores of 0.914 and more.Clinical relevance- The proposed method showed excellent agreements with the GAITRite system in analyzing spatiotemporal gait parameters. Our approach can be applied to monitor the elderly's health conditions based on their gait parameters for early diagnosis of diseases, proper treatment, and timely intervention.

Static and dynamic validation of kinect for ergonomic postural analysis using electro-goniometers as a gold standard:A preliminary study

BACKGROUND

Evaluation of the working postures and development of new techniques are paramount in reducing the awkward postures and occurrence of musculoskeletal disorders (MSDs). The Kinect sensor, a portable and cost-effective device, appears to be a promising alternative to study work postures.

OBJECTIVE

The current study aimed to evaluate the validity of Kinect against the gold-standard instrument (electro-goniometers) for body joint angle measurements.

METHODS

A unique software application was developed to measure the critical body joint angles for postural evaluation by using the Kinect's skeletal tracking feature. The body joint angle data of ten volunteers were measured simultaneously by both Kinect and electro-goniometers. The validation analysis was conducted in both static and dynamic domains of application.

RESULTS

Minimal variation was observed between the two techniques, and the Kinect correlated well for upper-arm joint angles of 45∘, 60∘ and 90∘; lower-arm joint angles of 30∘, 45∘, 60∘, and 90∘; straight neck position, neck joint angle at maximum possible flexion; straight trunk position, trunk bend angle at full flexion. In dynamic analysis, four out of five ICC values were > 0.75 except for the upper arm. Discrepancies in the results indicated the disapproval of Kinect for only wrist measurements.

CONCLUSION

The results of the static and dynamic studies gave a sufficient basis to consider the Kinect tool as an alternative to contemporary posture-based ergonomic evaluation methods.

A Novel Procedure for Knee Flexion Angle Estimation Based on Functionally Defined Coordinate Systems and Independent of the Marker Landmarks

Knee angles are kinematic quantities that are commonly presented in gait analysis reports. They are typically calculated as the relative angles between the anatomical coordinate systems rigidly attached to the femur and the tibia. To give these angles a biomechanical meaning, the coordinate systems must be defined with respect to some anatomical landmarks. For example, if one axis of the joint coordinate systems is directed along the knee flexion/extension axis, then the relative angle assumes the meaning of flexion/extension angle. Defining accurate anatomical coordinate systems is not an easy task, because it requires skills in marker placement, landmark identification and definition of a biomechanical model. In this paper, we present a novel method to (i) functionally define two coordinate systems attached to femur and tibia and (ii) functionally calculate the knee angle based on the relative differential kinematics between the previously defined coordinate systems. As the main limitation, this method is unable to provide an absolute measurement of the knee flexion/extension angle; however, it is able to accurately capture and display the relative angular motion of the knee. We show that our method produced consistent results even when the measured coordinate systems were randomly modified, removing any anatomical referencing. The proposed method has the advantage of being independent/invariant of the choice of the original coordinate systems of the femur and tibia, removing the need for accurate marker placement. Some major consequences are that (i) the markers may be placed on optimal landmarks, for example, minimizing the soft tissue artifacts or improving the subject's comfort, and (ii) there is no need for anatomical calibration when technical marker clusters/triads are used.

Assessing Walking Stability Based on Whole-Body Movement Derived from a Depth-Sensing Camera

Stability during walking is considered a crucial aspect of assessing gait ability. The current study aimed to assess walking stability by applying principal component analysis (PCA) to decompose three-dimensional (3D) whole-body kinematic data of 104 healthy young adults (21.9 ± 3.5 years, 54 females) derived from a depth-sensing camera into a set of movement components/synergies called "principal movements" (PMs), forming together to achieve the task goal. The effect of sex as the focus area was tested on three PCA-based variables computed for each PM: the relative explained variance (rVAR) as a measure of the composition of movement structures; the largest Lyapunov exponent (LyE) as a measure of variability; and the number of zero-crossings (N) as a measure of the tightness of neuromuscular control. The results show that the sex effects appear in the specific PMs. Specifically, in PM₁, resembling the swing-phase movement, females have greater LyE (p = 0.013) and N (p = 0.017) values than males. Moreover, in PM₃, representing the mid-stance-phase movement, females have smaller rVAR (p = 0.020) but greater N (p = 0.008) values than males. These empirical findings suggest that the inherent sex differences in walking stability should be considered in assessing and training locomotion.

Enabling Gait Analysis in the Telemedicine Practice through Portable and Accurate 3D Human Pose Estimation

Human pose estimation (HPE) through deep learning-based software applications is a trend topic for markerless motion analysis. Thanks to the accuracy of the state-of-the-art technology, HPE could enable gait analysis in the telemedicine practice. On the other hand, delivering such a service at a distance requires the system to satisfy multiple and different constraints like accuracy, portability, real-time, and privacy compliance at the same time. Existing solutions either guarantee accuracy and real-time (e.g., the widespread OpenPose software on well-equipped computing platforms) or portability and data privacy (e.g., light convolutional neural networks on mobile phones). We propose a portable and low-cost platform that implements real-time and accurate 3D HPE through an embedded software on a low-power off-the-shelf computing device that guarantees privacy by default and by design. We present an extended evaluation of both accuracy and performance of the proposed solution conducted with a marker-based motion capture system (i.e., Vicon) as ground truth. The results show that the platform achieves real-time performance and high-accuracy with a deviation below the error tolerance when compared to the marker-based motion capture system (e.g., less than an error of 5^∘ on the estimated knee flexion difference on the entire gait cycle and correlation 0.91<ρ<0.99). We provide a proof-of-concept study, showing that such portable technology, considering the limited discrepancies with respect to the marker-based motion capture system and its working tolerance, could be used for gait analysis at a distance without leading to different clinical interpretation.

Enhanced assessment of human dynamic stability by eliminating the effect of body height: modeling and experiment study

Margin of stability (MOS) is one of the essential indices for evaluating dynamic stability. However, there are indications that MOS was affected by body height and its application in identifying factors on dynamic stability other than body height is restricted. An inverted pendulum model was used to simulate human walking and investigate the relevance between MOS and body height. Eventually, a height-independent index in dynamic stability assessment (named as Angled Margin of Stability, AMOS) was proposed. For testing, fifteen healthy young volunteers performed walking trials with normal arm swing, holding arms, and anti-normal arm swing. Kinematic parameters were recorded using a gait analysis system with a Microsoft Kinect V2.0 and instrumented walkway. Both simulation and test results show that MOS had a significant correlation with height during walking with normal arm swing, while AMOS had no such significant correlation. Walking with normal arm swing produced significantly larger AMOS than holding arms and anti-normal arm swing. However, no significant difference showed up in MOS between normal arm swing and holding arms. The results suggest that AMOS is not affected by body height and has the potential to identify the variations in dynamic stability caused by physiological factors other than body height.

Comparison of Azure Kinect overground gait spatiotemporal parameters to marker based optical motion capture

BACKGROUND

Instrumented measurement of spatiotemporal parameters during walking can provide valuable information on an individual's overall function and health. Efficient, inexpensive, and accurate measurement of overground walking spatiotemporal parameters would be a critical component of providing point-of-care assessments of gait function, concussion recovery, fall-risk, and cognitive decline. Depth cameras combined with skeleton pose tracking algorithms, such as the Microsoft Kinect with body tracking software, have been used to measure walking spatiotemporal parameters. However, the ability of the latest generation Microsoft Kinect sensor, the Azure Kinect, to accurately measure overground walking spatiotemporal parameters has not been evaluated in the literature.

RESEARCH QUESTION

The purpose of this work was to compare overground walking spatiotemporal parameters measurements from a 12 camera Vicon optical motion capture system to measurements of a single Azure Kinect with body tracking SDK (software development kit).

METHODS

Spatiotemporal parameters of overground walking were simultaneously collected on twenty young healthy participants. Stride length, stride time, step length and step width were derived from ankle joint center locations and measurements from the two instruments were compared using descriptive statistics, scatter plots, Pearson correlation analyses, and Bland-Altman analyses.

RESULTS

Pearson correlation coefficients were greater than 0.87 for all spatiotemporal parameters with most parameters demonstrating very strong (> 0.9) agreement. The mean of the differences for stride length between measurements was 35.6 mm for the left limb and 39.1 mm for the right limb, both of which are less than 3% of average stride length. Mean of the differences for step width and stride time were less than 2% and 1% of their averages respectively.

SIGNIFICANCE

A single Microsoft Azure Kinect with body tracking SDK can provide clinically relevant measurement of walking spatiotemporal parameters, providing accessible and objective measurements that can improve clinical decision making across a variety of patient populations.

Placement Recommendations for Single Kinect-Based Motion Capture System in Unilateral Dynamic Motion Analysis

Low-cost, portable, and easy-to-use Kinect-based systems achieved great popularity in out-of-the-lab motion analysis. The placement of a Kinect sensor significantly influences the accuracy in measuring kinematic parameters for dynamics tasks. We conducted an experiment to investigate the impact of sensor placement on the accuracy of upper limb kinematics during a typical upper limb functional task, the drinking task. Using a 3D motion capture system as the golden standard, we tested twenty-one Kinect positions with three different distances and seven orientations. Upper limb joint angles, including shoulder flexion/extension, shoulder adduction/abduction, shoulder internal/external rotation, and elbow flexion/extension angles, are calculated via our developed Kinect kinematic model and the UWA kinematic model for both the Kinect-based system and the 3D motion capture system. We extracted the angles at the point of the target achieved (PTA). The mean-absolute-error (MEA) with the standard represents the Kinect-based system's performance. We conducted a two-way repeated measure ANOVA to explore the impacts of distance and orientation on the MEAs for all upper limb angles. There is a significant main effect for orientation. The main effects for distance and the interaction effects do not reach statistical significance. The post hoc test using LSD test for orientation shows that the effect of orientation is joint-dependent and plane-dependent. For a complex task (e.g., drinking), which involves body occlusions, placing a Kinect sensor right in front of a subject is not a good choice. We suggest that place a Kinect sensor at the contralateral side of a subject with the orientation around 30∘ to 45∘ for upper limb functional tasks. For all kinds of dynamic tasks, we put forward the following recommendations for the placement of a Kinect sensor. First, set an optimal sensor position for capture, making sure that all investigated joints are visible during the whole task. Second, sensor placement should avoid body occlusion at the maximum extension. Third, if an optimal location cannot be achieved in an out-of-the-lab environment, researchers could put the Kinect sensor at an optimal orientation by trading off the factor of distance. Last, for those need to assess functions of both limbs, the users can relocate the sensor and re-evaluate the functions of the other side once they finish evaluating functions of one side of a subject.